Part-Time Benchmarking Engineer (Remote)
Join Our Team and Shape the Future of AI Benchmarking! We're seeking a skilled and motivated Part-Time Benchmarking Engineer to play a key role in maintaining and improving our public LLM benchmarks. As a remote team member, you'll enjoy the freedom and flexibility to work from anywhere, with a competitive salary and the opportunity to grow with our company.
About the Role: As a Benchmarking Engineer, you will be responsible for creating new datasets, running benchmarks against new models, and analyzing results to provide valuable insights. You will have significant ownership of our benchmarking site and the opportunity to propose new benchmarks based on your ideas and hypotheses.
Key Responsibilities:
Create new, private datasets in conjunction with our data annotators and partner groups
Run existing benchmarks against new models and compile results
Write free-text analyses of raw quantitative results to answer key questions about model performance
Create social media posts to share our findings with the community
Maintain and improve scripts used to run benchmarks against our datasets
Requirements:
Deep experience with Python
Strong communication and writing skills
Experience working in teams, including development sprints and Git
Availability of approximately 20 hours per week
Nice to Haves:
Familiarity with LLM methods and developments
Experience in ML research setting or data science
About Us: At Vals AI, we're building the enterprise benchmark for LLM and LLM apps on real-world business tasks. Our mission is to create the infrastructure and certification to automatically audit LLM applications, verifying they are ready for consumption. We're a team of talented individuals with a passion for AI and a drive to make a difference.
What We Offer:
Competitive salary
Optional ability to work in our SF office
Opportunity to grow into a full-time role
Collaborative and dynamic work environment
How to Apply: If you're a motivated and skilled individual with a passion for AI, we encourage you to apply for this exciting opportunity. Don't worry if you don't meet every single requirement - we value a great attitude and a willingness to learn above all. Apply Now
Apply Now
About the Role: As a Benchmarking Engineer, you will be responsible for creating new datasets, running benchmarks against new models, and analyzing results to provide valuable insights. You will have significant ownership of our benchmarking site and the opportunity to propose new benchmarks based on your ideas and hypotheses.
Key Responsibilities:
Create new, private datasets in conjunction with our data annotators and partner groups
Run existing benchmarks against new models and compile results
Write free-text analyses of raw quantitative results to answer key questions about model performance
Create social media posts to share our findings with the community
Maintain and improve scripts used to run benchmarks against our datasets
Requirements:
Deep experience with Python
Strong communication and writing skills
Experience working in teams, including development sprints and Git
Availability of approximately 20 hours per week
Nice to Haves:
Familiarity with LLM methods and developments
Experience in ML research setting or data science
About Us: At Vals AI, we're building the enterprise benchmark for LLM and LLM apps on real-world business tasks. Our mission is to create the infrastructure and certification to automatically audit LLM applications, verifying they are ready for consumption. We're a team of talented individuals with a passion for AI and a drive to make a difference.
What We Offer:
Competitive salary
Optional ability to work in our SF office
Opportunity to grow into a full-time role
Collaborative and dynamic work environment
How to Apply: If you're a motivated and skilled individual with a passion for AI, we encourage you to apply for this exciting opportunity. Don't worry if you don't meet every single requirement - we value a great attitude and a willingness to learn above all. Apply Now
Apply Now